© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 237847
    Prev
    Next
    INDEX
    Explanations

    festive Christmas dishes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    zelfde
    0.51
     procedimiento
    0.48
    障
    0.48
     limpiar
    0.47
    ة
    0.47
    西部
    0.47
    大手
    0.47
    害
    0.46
    防止
    0.46
    幼稚
    0.46
    POSITIVE LOGITS
    ایه
    0.47
     为
    0.45
     वर्षे
    0.44
     yaşayan
    0.44
    rVert
    0.43
    ieros
    0.43
    urètre
    0.43
    ٹین
    0.42
    य्
    0.42
     তারা
    0.42
    Activations Density 0.000%

    No Known Activations